© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118250
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     однозна
    -0.07
    ;
    -0.06
     людьми
    -0.06
     給
    -0.06
    这样的
    -0.06
    憧
    -0.06
    ；
    -0.06
    ต่อไป
    -0.06
     diamètre
    -0.06
     storied
    -0.06
    POSITIVE LOGITS
     mily
    0.07
     malfunctioning
    0.06
     Ehrlich
    0.06
     Bericht
    0.06
     قادر
    0.06
    𒌓
    0.06
    वन
    0.06
     सऊदी
    0.06
     failure
    0.06
    ỏe
    0.06
    Activations Density 0.000%

    No Known Activations